agentmods.dev

open-harness: Skill for Claude Code

.agents/skills/release-local/SKILL.md

release-local is a skill for Claude Code from MaxGfeller/open-harness. It costs 21 tokens per session (281 once invoked), scanned A, original, MIT.

A guided release procedure for a pnpm monorepo, a repository containing multiple related packages, that uses Changesets to manage version updates and release notes.

In plain words
What is it for?
It checks pending changesets, updates package versions and changelogs, prepares the release commit, publishes packages to npm, and creates or repairs GitHub Releases.
Why use it?
It reduces the risk of publishing from the wrong branch, releasing with uncommitted changes, or accidentally publishing packages and GitHub tags without confirmation.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is MaxGfeller/open-harness's own configuration. It tells Claude Code how to work on open-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-harness configures →

not rated 622repo 3mo ago A scan SkillSpector: pass 21 tokens original MIT
View source ↗ MaxGfeller/open-harness open-harness.dev
Reuse

Borrowing it

Nothing to install: this file belongs to MaxGfeller/open-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MaxGfeller/open-harness/main/.agents/skills/release-local/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MaxGfeller/open-harness

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for release-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxgfeller/open-harness/release-local/github.svg)](https://agentmods.dev/skills/maxgfeller/open-harness/release-local)
Your own site
<a href="https://agentmods.dev/skills/maxgfeller/open-harness/release-local"><img src="https://agentmods.dev/badge/skills/maxgfeller/open-harness/release-local/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for release-local

Your own site · 80×15
<a href="https://agentmods.dev/skills/maxgfeller/open-harness/release-local"><img src="https://agentmods.dev/badge/skills/maxgfeller/open-harness/release-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 281 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00281
Opus 5.5 $0.00008 $0.00112
Sonnet 5.5 $0.00004 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 2mo ago against content hash b51eedce4af7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-local scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/release-local/SKILL.md · 27 lines

What it actually says

Run the release workflow from RELEASING.md.

Guardrails:

  • Only run this on main unless the user explicitly wants a dry run elsewhere.
  • Require a clean worktree before versioning or publishing.
  • Ask for confirmation before creating the release commit.
  • Ask for confirmation again before starting pnpm release:publish, because it publishes to npm, pushes the branch and tags to GitHub, and may require npm OTP entry.

Workflow:

  1. Run pnpm release:status and confirm there are pending changesets.
  2. Run pnpm version-packages.
  3. Review the generated version bumps and changelog entries with the user.
  4. Commit the release files with Release packages unless the user requests a different message.
  5. Run pnpm release:publish.
  6. Confirm that npm publish succeeded and that GitHub Releases were created or updated for the tags on HEAD.
  7. If npm publish succeeded but GitHub release creation failed, rerun pnpm release:github after fixing the blocker.

If publish fails because of npm auth, OTP, or missing release notes, stop, report the exact blocker, and do not keep mutating the repo.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 27 lines · 21 tokens per session scan A b51eedce4af7

Subscribe to this mod's changes

release-local is a skill published in the GitHub repository MaxGfeller/open-harness (622 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 281 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowReleasesagentsagentskillsaiai-agentsmcp
Related

release-local compared with skills from other repositories

release-local next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
release-localMaxGfeller/open-harnessSkill6223mo agoMITA21Claude Code
shipSnowflake-Labs/cocoplusSkill7272d agoMITA41Claude Code, Codex
exit-strategykucherenko/gangstaSkill8710d agoMITA32Claude Code
apply-semantic-versioningpjt222/agent-almanacSkill43yesterdayMITA94Claude Code
create-github-releasepjt222/agent-almanacSkill43yesterdayMITA73Claude Code
project-release-maintainern-n-code/n-n-code-skillsSkill45d agoMITA41Claude Code, Codex
release-skillswpank/aiSkill128mo agononeA103Claude Code, Codex